Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization

Kevin J. Shih, Arun Mallya, Saurabh Singh and Derek Hoiem

Abstract

We present a simple deep learning framework to simultaneously predict keypoint locations and their respective visibilities and use those to achieve state-of-the-art performance for fine-grained classification. We show that by conditioning the predictions on object proposals with sufficient image support, our method can do well without complicated spatial reasoning. Instead, inference methods with robustness to outliers, yield state-of-the-art for keypoint localization. We demonstrate the effectiveness of our accurate keypoint localization and visibility prediction on the fine-grained bird recognition task with and without ground truth bird bounding boxes, and outperform existing state-of-the-art methods by over 2%.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 155K)
PDF iconPaper (PDF, 5M)

DOI

10.5244/C.29.128
https://dx.doi.org/10.5244/C.29.128

Citation

Kevin J. Shih, Arun Mallya, Saurabh Singh and Derek Hoiem. Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 128.1-128.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_128,
	title={Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization},
	author={Kevin J. Shih and Arun Mallya and Saurabh Singh and Derek Hoiem},
	year={2015},
	month={September},
	pages={128.1-128.12},
	articleno={128},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.128},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.128}
}